6 papers
Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries
Chonghe Jiang, Ao Qu, Siyuan Liu +9
Open-ended scientific discovery often requires repeatedly proposing and evaluating candidate solutions. LLM-based systems can support this process by generating and refining execut…
Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents
Howard Wang, Han Zheng, Cathy Wu
In a decentralized multi-robot team under partial observability, the fact that decides a robot's next action is often visible only to a teammate. Existing decentralized methods com…
FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
Minwei Kong, Chonghe Jiang, Ao Qu +24
Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimization problems often require a…
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
Tianyu Wu, Yu Yao, Zhenting Qi +7
Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters su…
OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space
Zhiyuan Cao, Zeyu Ma, Chenhao Yang +2
We propose Obfuscated Semantic Null space Injection for Privacy (OSNIP), a lightweight client-side encryption framework for privacy-preserving LLM inference. Generalizing the geome…
Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models
Wanying Wang, Zeyu Ma, Han Zheng +2
Large vision-language models (LVLMs) are vulnerable to harmful input compared to their language-only backbones. We investigated this vulnerability by exploring LVLMs internal dynam…